PDF Publication Title:
Text from PDF Page: 180
Table 6. Classification metrics when using training data generated by several over-sampling algorithms. 4.3. Model training As part of the different experiments performed, we have learned that the inclusion of regularization by using drop-out provides worse results, similarly to increasing the number of layers for the encoder and decoder beyond 2 or 3 layers. We have seen also that results are sensitive to the number of training epochs, having better results when this number is over 50. All the models converged easily. Table 7 presents the parameters used for the training of the different models. We have used Tensorflow to implement all the VAE models, and the python package scikit- learn to implement the different classifiers. All computations have been performed in a commercial PC (i7-4720-HQ, 16GB RAM). Table 7. Parameters used to train the models 5. Discussion and conclusion This work is unique in presenting the application of a VAE as a generative model for intrusion detection. The model is able to synthesize data with both continuous and categorical features. We have demonstrated that the data generated is similar to the original data, and, at the same time, have enough variability to be effective in improving the detection performance of several classifiers when used together with the original data. Other aspect unique to this work is the ability to synthesize the new samples from the intrusion labels to which the synthetic data should belong, with the advantage of not relying on Doctoral Thesis: Novel applications of Machine Learning to NTAP - 178PDF Image | Novel applications of Machine Learning to Network Traffic Analysis
PDF Search Title:
Novel applications of Machine Learning to Network Traffic AnalysisOriginal File Name Searched:
456453_1175348.pdfDIY PDF Search: Google It | Yahoo | Bing
Cruise Ship Reviews | Luxury Resort | Jet | Yacht | and Travel Tech More Info
Cruising Review Topics and Articles More Info
Software based on Filemaker for the travel industry More Info
The Burgenstock Resort: Reviews on CruisingReview website... More Info
Resort Reviews: World Class resorts... More Info
The Riffelalp Resort: Reviews on CruisingReview website... More Info
CONTACT TEL: 608-238-6001 Email: greg@cruisingreview.com (Standard Web Page)